Fine-tune url-value HTML attributes list.

pelican/contents.py

@@ -125,52 +125,6 @@ class Content(object):
         if 'summary' in metadata:
             self._summary = metadata['summary']
 
-        # prepare the list of HTML tag attributes which have a URL value.
-        # refer: http://stackoverflow.com/questions/2725156/complete-list-of-html-tag-attributes-which-have-a-url-value
-        self._url_attributes = {  # each item in this set is a tuple composed by tag_name, attr_name
-            # HTML4 tags
-            ('a', 'href'),
-            ('applet', 'codebase'),
-            ('area', 'href'),
-            ('base', 'href'),
-            ('blockquote', 'cite'),
-            ('body', 'background'),
-            ('del', 'cite'),
-            ('form', 'action'),
-            ('frame', 'longdesc'),
-            ('frame', 'src'),
-            ('head', 'profile'),
-            ('iframe', 'longdesc'),
-            ('iframe', 'src'),
-            ('img', 'longdesc'),
-            ('img', 'src'),
-            ('img', 'usemap'),
-            ('input', 'src'),
-            ('input', 'usemap'),
-            ('ins', 'cite'),
-            ('link', 'href'),
-            ('object', 'classid'),
-            ('object', 'codebase'),
-            ('object', 'data'),
-            ('object', 'usemap'),
-            ('q', 'cite'),
-            ('script', 'src'),
-
-            # HTML5 tags
-            ('audio', 'src'),
-            ('button', 'formaction'),
-            ('command', 'icon'),
-            ('embed', 'src'),
-            ('html', 'manifest'),
-            ('input', 'formaction'),
-            ('source', 'src'),
-            ('video', 'poster'),
-            ('video', 'src'),
-        }
-        """:type: set of (tuple of (string, string)"""
-        attribute_names = set(pair[1] for pair in self._url_attributes)
-        self._url_attr_pattern = '|'.join(attribute_names)
-
         signals.content_object_init.send(self)
 
     def __str__(self):
@@ -235,12 +189,12 @@ class Content(object):
 
         instrasite_link_regex = self.settings['INTRASITE_LINK_REGEX']
         regex = r"""
-            (?P<markup><\s*(?P<tag>[^\s\>]+)[^\>]*  # match tag with all url-value attributes
+            (?P<markup><\s*[^\>]*  # match tag with all url-value attributes
-                (?P<attr>{1})\s*=)
+                (?:href|src|poster|data|cite|formaction|action)\s*=)
 
             (?P<quote>["\'])      # require value to be quoted
             (?P<path>{0}(?P<value>.*?))  # the url value
-            \4""".format(instrasite_link_regex, self._url_attr_pattern)
+            \2""".format(instrasite_link_regex)
         hrefs = re.compile(regex, re.X)
 
         def replacer(m):
@@ -249,12 +203,6 @@ class Content(object):
             path = value.path
             origin = m.group('path')
 
-            # verify HTML tag and attribute pair to avoid miss-replacing
-            tag = m.group('tag')
-            attr = m.group('attr')
-            if attr != 'href' and attr != 'src' and (tag, attr) not in self._url_attributes:
-                return m.group(0)
-
             # XXX Put this in a different location.
             if what == 'filename':
                 if path.startswith('/'):

pelican/tests/test_contents.py

@@ -268,6 +268,61 @@ class TestPage(unittest.TestCase):
             '?utm_whatever=234&highlight=word#section-2">link</a>'
         )
 
+    def test_intrasite_link_more(self):
+        # type does not take unicode in PY2 and bytes in PY3, which in
+        # combination with unicode literals leads to following insane line:
+        cls_name = '_DummyAsset' if six.PY3 else b'_DummyAsset'
+
+        args = self.page_kwargs.copy()
+        args['settings'] = get_settings()
+        args['source_path'] = 'content'
+        args['context']['filenames'] = {
+            'images/poster.jpg': type(cls_name, (object,), {'url': 'images/poster.jpg'}),
+            'assets/video.mp4': type(cls_name, (object,), {'url': 'assets/video.mp4'}),
+            'images/graph.svg': type(cls_name, (object,), {'url': 'images/graph.svg'}),
+            'reference.rst': type(cls_name, (object,), {'url': 'reference.html'}),
+        }
+
+        # video.poster
+        args['content'] = (
+            'There is a video with poster '
+            '<video controls poster="{filename}/images/poster.jpg">'
+            '<source src="|filename|/assets/video.mp4" type="video/mp4">'
+            '</video>'
+        )
+        content = Page(**args).get_content('http://notmyidea.org')
+        self.assertEqual(
+            content,
+            'There is a video with poster '
+            '<video controls poster="http://notmyidea.org/images/poster.jpg">'
+            '<source src="http://notmyidea.org/assets/video.mp4" type="video/mp4">'
+            '</video>'
+        )
+
+        # object.data
+        args['content'] = (
+            'There is a svg object '
+            '<object data="{filename}/images/graph.svg" type="image/svg+xml"></object>'
+        )
+        content = Page(**args).get_content('http://notmyidea.org')
+        self.assertEqual(
+            content,
+            'There is a svg object '
+            '<object data="http://notmyidea.org/images/graph.svg" type="image/svg+xml"></object>'
+        )
+
+        # blockquote.cite
+        args['content'] = (
+            'There is a blockquote with cite attribute '
+            '<blockquote cite="{filename}reference.rst">blah blah</blockquote>'
+        )
+        content = Page(**args).get_content('http://notmyidea.org')
+        self.assertEqual(
+            content,
+            'There is a blockquote with cite attribute '
+            '<blockquote cite="http://notmyidea.org/reference.html">blah blah</blockquote>'
+        )
+
 
 class TestArticle(TestPage):
     def test_template(self):